kbd-vits-tts-male / config_3.json
anzorq's picture
Upload config_3.json with huggingface_hub
26ccbcf
{
"output_path": "/kaggle/working/train_output",
"logger_uri": null,
"run_name": "vits_kbd_male",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 25,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"save_on_interrupt": true,
"log_model_step": null,
"save_step": 1000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 10000,
"target_loss": null,
"print_eval": true,
"test_delay_epochs": -1,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": false,
"precision": "fp16",
"epochs": 1000,
"batch_size": 32,
"eval_batch_size": 16,
"grad_clip": [
1000,
1000
],
"scheduler_after_epoch": true,
"lr": 0.001,
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"weight_decay": 0.01
},
"lr_scheduler": null,
"lr_scheduler_params": {},
"use_grad_scaler": false,
"allow_tf32": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "vits",
"num_loader_workers": 0,
"num_eval_loader_workers": 2,
"use_noise_augment": false,
"audio": {
"fft_size": 1024,
"win_length": 1024,
"hop_length": 256,
"frame_shift_ms": null,
"frame_length_ms": null,
"stft_pad_mode": "reflect",
"sample_rate": 24000,
"resample": false,
"preemphasis": 0.0,
"ref_level_db": 20,
"do_sound_norm": false,
"log_func": "np.log10",
"do_trim_silence": true,
"trim_db": 45,
"do_rms_norm": false,
"db_level": null,
"power": 1.5,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 0,
"mel_fmax": null,
"spec_gain": 20,
"do_amp_to_db_linear": true,
"do_amp_to_db_mel": true,
"pitch_fmax": 640.0,
"pitch_fmin": 1.0,
"signal_norm": true,
"min_level_db": -100,
"symmetric_norm": true,
"max_norm": 4.0,
"clip_norm": true,
"stats_path": null
},
"use_phonemes": false,
"phonemizer": null,
"phoneme_language": null,
"compute_input_seq_cache": true,
"text_cleaner": "basic_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": "/kaggle/working/train_output/phoneme_cache",
"characters": {
"characters_class": "TTS.tts.utils.text.characters.Graphemes",
"vocab_dict": null,
"pad": "<PAD>",
"eos": "<EOS>",
"bos": "<BOS>",
"blank": "<BLNK>",
"characters": "abnhikorst\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u04cf",
"punctuations": "!\"(),-.:?\u00ab\u00bb\u2013 ",
"phonemes": "",
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"batch_group_size": 5,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": Infinity,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": true,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "mozilla",
"dataset_name": "",
"path": "/kaggle/input/circassian-kbd-tts-male",
"meta_file_train": "metadata.csv",
"ignored_speakers": null,
"language": "",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
[
"\u0441\u0438 \u043d\u044d\u0445\u0443\u043d\u044d\u0440 \u043a\u044a\u044d\u0445\u044a\u0443\u0443\u044d \u0449\u044b\u0442\u043c\u044d \u043b\u04cf\u044b \u0445\u044d\u043a\u04cf\u044b\u043d\u0449"
],
[
"\u043a\u044a\u044b\u0444\u04cf\u044d\u0433\u044a\u044d\u043d\u044d\u043d"
],
[
"\u0443\u0438 \u0443\u043d\u044d\u0436\u044c \u0445\u0443\u044d\u0434\u044d \u0449\u044b\u04cf\u044d\u043a\u044a\u044b\u043c"
],
[
"\u0442\u0445\u044b\u043b\u044a \u043f\u04cf\u0430\u0449\u044d\u0440 \u0437\u044b\u0442\u0435\u0443\u0445\u0443\u0430\u0440"
],
[
"\u043b\u044a\u044b\u043f\u0446\u04cf\u044d"
],
[
"\u043f\u0449\u044b\u0445\u044c\u044d\u0449\u0445\u044c\u044d\u0440 \u0434\u0430\u0443\u044d \u0431\u0433\u044a\u044d\u043a\u04cf\u0443\u044d\u043d\u0443?|"
],
[
"\u043b\u044d\u0436\u044c\u0430\u043f\u04cf\u044d\u043d\u0448\u0430\u0433\u044a\u044d"
],
[
"\u0437\u044b\u043a\u044a\u044b\u043a\u04cf\u0443\u044d\u0446\u04cf\u044b\u0437\u0433\u044a\u044d\u0434\u0436\u044d\u0440\u044d\u0437\u044b\u043a\u04cf\u044b\u0436\u044b\u0444\u0430 \u043c\u044b\u0433\u044a\u0443\u044d\u043a\u044a\u044b\u043c"
],
[
"\u043f\u0441\u043e\u0440\u0438 \u0437\u044d\u0440\u044b\u0443\u0437\u044b\u043d\u0448\u044d\u0440 \u043d\u044d\u0445\u044a\u0430\u043f\u044d\u0449"
]
],
"eval_split_max_size": null,
"eval_split_size": 0.01,
"use_speaker_weighted_sampler": false,
"speaker_weighted_sampler_alpha": 1.0,
"use_language_weighted_sampler": false,
"language_weighted_sampler_alpha": 1.0,
"use_length_weighted_sampler": false,
"length_weighted_sampler_alpha": 1.0,
"model_args": {
"num_chars": 60,
"out_channels": 513,
"spec_segment_size": 32,
"hidden_channels": 192,
"hidden_channels_ffn_text_encoder": 768,
"num_heads_text_encoder": 2,
"num_layers_text_encoder": 6,
"kernel_size_text_encoder": 3,
"dropout_p_text_encoder": 0.1,
"dropout_p_duration_predictor": 0.5,
"kernel_size_posterior_encoder": 5,
"dilation_rate_posterior_encoder": 1,
"num_layers_posterior_encoder": 16,
"kernel_size_flow": 5,
"dilation_rate_flow": 1,
"num_layers_flow": 4,
"resblock_type_decoder": "1",
"resblock_kernel_sizes_decoder": [
3,
7,
11
],
"resblock_dilation_sizes_decoder": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"upsample_rates_decoder": [
8,
8,
2,
2
],
"upsample_initial_channel_decoder": 512,
"upsample_kernel_sizes_decoder": [
16,
16,
4,
4
],
"periods_multi_period_discriminator": [
2,
3,
5,
7,
11
],
"use_sdp": true,
"noise_scale": 1.0,
"inference_noise_scale": 0.667,
"length_scale": 1,
"noise_scale_dp": 1.0,
"inference_noise_scale_dp": 1.0,
"max_inference_len": null,
"init_discriminator": true,
"use_spectral_norm_disriminator": false,
"use_speaker_embedding": false,
"num_speakers": 0,
"speakers_file": null,
"d_vector_file": null,
"speaker_embedding_channels": 256,
"use_d_vector_file": false,
"d_vector_dim": 0,
"detach_dp_input": true,
"use_language_embedding": false,
"embedded_language_dim": 4,
"num_languages": 0,
"language_ids_file": null,
"use_speaker_encoder_as_loss": false,
"speaker_encoder_config_path": "",
"speaker_encoder_model_path": "",
"condition_dp_on_speaker": true,
"freeze_encoder": false,
"freeze_DP": false,
"freeze_PE": false,
"freeze_flow_decoder": false,
"freeze_waveform_decoder": false,
"encoder_sample_rate": null,
"interpolate_z": true,
"reinit_DP": false,
"reinit_text_encoder": false
},
"lr_gen": 0.0002,
"lr_disc": 0.0002,
"lr_scheduler_gen": "ExponentialLR",
"lr_scheduler_gen_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"lr_scheduler_disc": "ExponentialLR",
"lr_scheduler_disc_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"kl_loss_alpha": 1.0,
"disc_loss_alpha": 1.0,
"gen_loss_alpha": 1.0,
"feat_loss_alpha": 1.0,
"mel_loss_alpha": 45.0,
"dur_loss_alpha": 1.0,
"speaker_encoder_loss_alpha": 1.0,
"return_wav": true,
"use_weighted_sampler": false,
"weighted_sampler_attrs": {},
"weighted_sampler_multipliers": {},
"r": 1,
"num_speakers": 0,
"use_speaker_embedding": false,
"speakers_file": null,
"speaker_embedding_channels": 256,
"language_ids_file": null,
"use_language_embedding": false,
"use_d_vector_file": false,
"d_vector_file": null,
"d_vector_dim": 0,
"github_branch": "inside_docker"
}